PROJECT TITLE :

Wireless Resource Scheduling in Virtualized Radio Access Networks Using Stochastic Learning - 2018

ABSTRACT:

How to allocate the restricted wireless resource in dense radio access networks (RANs) remains challenging. By leveraging a software-outlined control plane, the freelance base stations (BSs) are virtualized as a centralized network controller (CNC). Such virtualization decouples the CNC from the wireless service providers (WSPs). We investigate a virtualized RAN, where the CNC auctions channels at the start of scheduling slots to the mobile terminals (MTs) based mostly on bids from their subscribing WSPs. Each WSP aims at maximizing the expected long-term payoff from bidding channels to satisfy the MTs for transmitting packets. We tend to formulate the matter as a stochastic game, where the channel auction and packet scheduling choices of a WSP rely on the state of network and therefore the control policies of its competitors. To approach the equilibrium solution, an abstract stochastic game is proposed with bounded regret. The decision creating method of every WSP is modeled as a Markov decision process (MDP). To address the signalling overhead and computational complexity problems, we have a tendency to decompose the MDP into a series of single-agent MDPs with reduced state areas, and derive an online localized algorithm to be told the state value functions. Our results show vital performance improvements in terms of per-MT average utility.